© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20592
    Prev
    Next
    INDEX
    Explanations

    late days of the week

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on names of weekdays (e.g., “Tuesday,” “Wednesday”) in news timestamps or datelines.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vivió
    -1.64
     posando
    -1.62
     listos
    -1.56
     kurzem
    -1.55
     vivía
    -1.55
     aprobó
    -1.53
     extremadamente
    -1.52
    ݮ
    -1.50
    ௅
    -1.50
     pequena
    -1.49
    POSITIVE LOGITS
     of
    2.27
     was
    1.56
    します
    1.52
    他的
    1.51
    しました
    1.51
     also
    1.47
    么
    1.42
    "
    1.38
    事情
    1.37
     from
    1.35
    Activations Density 0.007%

    No Known Activations